SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

🚨 🚨 Setup -> setupclass conversion (#37282)

Browse Source 
* More limited setup -> setupclass conversion

* make fixup

* Trigger tests

* Fixup UDOP

* Missed a spot

* tearDown -> tearDownClass where appropriate

* Couple more class fixes

* Fixups for UDOP and VisionTextDualEncoder

* Ignore errors when removing the tmpdir, in case it already got cleaned up somewhere

* CLIP fixes

* More correct classmethods

* Wav2Vec2Bert fixes

* More methods become static

* More class methods

* More class methods

* Revert changes for integration tests / modeling files

* Use a different tempdir for tests that actually write to it

* Remove addClassCleanup and just use teardownclass

* Remove changes in modeling files

* Cleanup get_processor_dict() for got_ocr2

* Fix regression on Wav2Vec2BERT test that was masked by this before

* Rework tests that modify the tmpdir

* make fix-copies

* revert clvp modeling test changes

* Fix CLIP processor test

* make fix-copies
This commit is contained in:
Matt
2025-04-08 17:15:37 +01:00
committed by GitHub
parent c15a7adb28
commit 4d0de5f73a
49 changed files with 740 additions and 574 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
tests/models/pix2struct/test_processor_pix2struct.py
View File

@@ -40,15 +40,16 @@ class Pix2StructProcessorTest(ProcessorTesterMixin, unittest.TestCase):
text_input_name = "decoder_input_ids"
images_input_name = "flattened_patches"
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
@classmethod
def setUpClass(cls):
cls.tmpdirname = tempfile.mkdtemp()
image_processor = Pix2StructImageProcessor()
tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-small")
processor = Pix2StructProcessor(image_processor, tokenizer)
processor.save_pretrained(self.tmpdirname)
processor.save_pretrained(cls.tmpdirname)
def get_tokenizer(self, **kwargs):
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).tokenizer
@@ -56,19 +57,21 @@ class Pix2StructProcessorTest(ProcessorTesterMixin, unittest.TestCase):
def get_image_processor(self, **kwargs):
return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
def tearDown(self):
shutil.rmtree(self.tmpdirname)
@classmethod
def tearDownClass(cls):
shutil.rmtree(cls.tmpdirname, ignore_errors=True)
def test_save_load_pretrained_additional_features(self):
processor = Pix2StructProcessor(tokenizer=self.get_tokenizer(), image_processor=self.get_image_processor())
processor.save_pretrained(self.tmpdirname)
with tempfile.TemporaryDirectory() as tmpdir:
processor = Pix2StructProcessor(tokenizer=self.get_tokenizer(), image_processor=self.get_image_processor())
processor.save_pretrained(tmpdir)
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
image_processor_add_kwargs = self.get_image_processor(do_normalize=False, padding_value=1.0)
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
image_processor_add_kwargs = self.get_image_processor(do_normalize=False, padding_value=1.0)
processor = Pix2StructProcessor.from_pretrained(
self.tmpdirname, bos_token="(BOS)", eos_token="(EOS)", do_normalize=False, padding_value=1.0
)
processor = Pix2StructProcessor.from_pretrained(
tmpdir, bos_token="(BOS)", eos_token="(EOS)", do_normalize=False, padding_value=1.0
)
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())
self.assertIsInstance(processor.tokenizer, PreTrainedTokenizerFast)